{"id":"W2906501467","doi":"10.15353/jcvis.v4i1.329","title":"On Robustness of Deep Neural Networks: A Comprehensive Study on the Effect of Architecture and Weight Initialization to Susceptibility and Transferability of Adversarial Attacks","year":2018,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Robustness (evolution); Initialization; Transferability; Computer science; Adversarial system; Artificial neural network; Network architecture; Artificial intelligence; Network model; Architecture; Machine learning; Data mining; Computer security","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001186518,0.0001562933,0.0004802851,0.0001880867,0.0001243616,0.00005783334,0.0002243381,0.00003358076,0.000001762986],"category_scores_gemma":[0.0002674883,0.00009752488,0.00005966092,0.0002444231,0.0002283177,0.0001851455,0.00009619967,0.0002199814,4.806493e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002001959,"about_ca_system_score_gemma":0.00002187012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001732058,"about_ca_topic_score_gemma":0.000002159398,"domain_scores_codex":[0.9973859,0.001138622,0.0006522809,0.0002070616,0.0005132428,0.0001029139],"domain_scores_gemma":[0.9964348,0.002293818,0.0004930174,0.0001672367,0.0005412863,0.00006981812],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007192774,0.00008305981,0.0165687,0.0001014536,0.00004546878,0.000002007518,0.002496449,0.9710317,0.0001644561,0.0005402032,0.00001207362,0.008235187],"study_design_scores_gemma":[0.001495468,0.003261207,0.0909337,0.0002175429,0.00002927335,0.00004127907,0.0002876538,0.9033528,0.00005419263,0.0002477771,0.00000280035,0.00007631955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5218117,0.00004508715,0.4773865,0.0001962036,0.0002945463,0.00025625,0.000001219707,0.000003529753,0.000004995964],"genre_scores_gemma":[0.9986021,0.000001115203,0.001194298,0.00003576414,0.0001577271,0.000001329243,7.566981e-7,0.000006640468,2.947008e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4767904,"threshold_uncertainty_score":0.3976949,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009030126548489809,"score_gpt":0.2898208874482386,"score_spread":0.2807907608997487,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}